github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-09 03:12:11 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

Delete partially downloaded models not working in wsl2 #8410

New Issue
Closed
opened 2025-11-12 14:41:11 -06:00 by GiteaMirror · 6 comments
GiteaMirror commented 2025-11-12 14:41:11 -06:00
Owner
Copy Link

Originally created by @somera on GitHub (Oct 16, 2025).

What is the issue?

I started downloading the new model hf.co/unsloth/gpt-oss-20b-GGUF:Q6_K but stopped the download. As noted in https://github.com/ollama/ollama/issues/1599, any partially downloaded files should be removed when Ollama starts (OLLAMA_CONTEXT_LENGTH=24576 OLLAMA_HOST=0.0.0.0 ollama serve).

This is not working for me:

$ ls -al ~/.ollama/models/blobs/*partial*
-rw-r--r-- 1 somera somera 12G Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial
-rw-r--r-- 1 somera somera  57 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-0
-rw-r--r-- 1 somera somera  65 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-1
-rw-r--r-- 1 somera somera  67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-10
-rw-r--r-- 1 somera somera  67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-11
-rw-r--r-- 1 somera somera  67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-12
-rw-r--r-- 1 somera somera  67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-13
-rw-r--r-- 1 somera somera  68 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-14
-rw-r--r-- 1 somera somera  68 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-15
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-2
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-3
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-4
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-5
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-6
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-7
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-8
-rw-r--r-- 1 somera somera  66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-9

Relevant log output

OS

WSL2

GPU

Nvidia

CPU

AMD

Ollama version

0.12.5

Originally created by @somera on GitHub (Oct 16, 2025). ### What is the issue? I started downloading the new model `hf.co/unsloth/gpt-oss-20b-GGUF:Q6_K` but stopped the download. As noted in https://github.com/ollama/ollama/issues/1599, any partially downloaded files should be removed when Ollama starts (OLLAMA_CONTEXT_LENGTH=24576 OLLAMA_HOST=0.0.0.0 ollama serve). This is not working for me: ``` $ ls -al ~/.ollama/models/blobs/*partial* -rw-r--r-- 1 somera somera 12G Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial -rw-r--r-- 1 somera somera 57 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-0 -rw-r--r-- 1 somera somera 65 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-1 -rw-r--r-- 1 somera somera 67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-10 -rw-r--r-- 1 somera somera 67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-11 -rw-r--r-- 1 somera somera 67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-12 -rw-r--r-- 1 somera somera 67 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-13 -rw-r--r-- 1 somera somera 68 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-14 -rw-r--r-- 1 somera somera 68 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-15 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-2 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-3 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-4 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-5 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-6 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-7 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-8 -rw-r--r-- 1 somera somera 66 Oct 16 19:56 /home/somera/.ollama/models/blobs/sha256-f2ead52a7842a556ea10d5edd91a88e5af974856d2485ecaad3aade679832935-partial-9 ``` ### Relevant log output ```shell ``` ### OS WSL2 ### GPU Nvidia ### CPU AMD ### Ollama version 0.12.5
GiteaMirror added the bug label 2025-11-12 14:41:11 -06:00
GiteaMirror commented 2025-11-12 14:41:13 -06:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 16, 2025):

Do you have OLLAMA_NO_PRUNE set in the server environment?

@rick-github commented on GitHub (Oct 16, 2025): Do you have `OLLAMA_NO_PRUNE` set in the server environment?
GiteaMirror commented 2025-11-12 14:41:13 -06:00
Author
Owner
Copy Link

@somera commented on GitHub (Oct 16, 2025):

Nope. I start Ollama manually:

OLLAMA_CONTEXT_LENGTH=24576 OLLAMA_HOST=0.0.0.0 ollama serve

or

OLLAMA_HOST=0.0.0.0 ollama serve

@somera commented on GitHub (Oct 16, 2025): Nope. I start Ollama manually: `OLLAMA_CONTEXT_LENGTH=24576 OLLAMA_HOST=0.0.0.0 ollama serve` or `OLLAMA_HOST=0.0.0.0 ollama serve`
GiteaMirror commented 2025-11-12 14:41:13 -06:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 16, 2025):

What's the first 10 lines of log when you start ollama?

@rick-github commented on GitHub (Oct 16, 2025): What's the first 10 lines of log when you start ollama?
GiteaMirror commented 2025-11-12 14:41:13 -06:00
Author
Owner
Copy Link

@somera commented on GitHub (Oct 16, 2025):

I see OLLAMA_NOPRUNE:false in

$ OLLAMA_HOST=0.0.0.0 ollama serve
time=2025-10-16T22:08:24.266+02:00 level=INFO source=routes.go:1481 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/somera/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-10-16T22:08:24.294+02:00 level=WARN source=routes.go:1493 msg="corrupt manifests detected, skipping prune operation.  Re-pull or delete to clear" error="registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M EOF"
time=2025-10-16T22:08:24.295+02:00 level=INFO source=routes.go:1534 msg="Listening on [::]:11434 (version 0.12.5)"
time=2025-10-16T22:08:24.297+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..."
time=2025-10-16T22:08:26.094+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-12ee681d-be61-a8c4-4271-304292804c1c library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4060 Ti" libdirs=ollama,cuda_v13 driver=13.0 pci_id=01:00.0 type=discrete total="16.0 GiB" available="14.9 GiB"
time=2025-10-16T22:08:26.095+02:00 level=INFO source=routes.go:1575 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"

I can't find any informations about OLLAMA_NO_PRUNE.

Or this

corrupt manifests detected, skipping prune operation. Re-pull or delete to clear" error="registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M EOF

is the first problem?

@somera commented on GitHub (Oct 16, 2025): I see `OLLAMA_NOPRUNE:false` in ``` $ OLLAMA_HOST=0.0.0.0 ollama serve time=2025-10-16T22:08:24.266+02:00 level=INFO source=routes.go:1481 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/somera/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-10-16T22:08:24.294+02:00 level=WARN source=routes.go:1493 msg="corrupt manifests detected, skipping prune operation. Re-pull or delete to clear" error="registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M EOF" time=2025-10-16T22:08:24.295+02:00 level=INFO source=routes.go:1534 msg="Listening on [::]:11434 (version 0.12.5)" time=2025-10-16T22:08:24.297+02:00 level=INFO source=runner.go:80 msg="discovering available GPUs..." time=2025-10-16T22:08:26.094+02:00 level=INFO source=types.go:112 msg="inference compute" id=GPU-12ee681d-be61-a8c4-4271-304292804c1c library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4060 Ti" libdirs=ollama,cuda_v13 driver=13.0 pci_id=01:00.0 type=discrete total="16.0 GiB" available="14.9 GiB" time=2025-10-16T22:08:26.095+02:00 level=INFO source=routes.go:1575 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" ``` I can't find any informations about `OLLAMA_NO_PRUNE`. Or this `corrupt manifests detected, skipping prune operation. Re-pull or delete to clear" error="registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M EOF` is the first problem?
GiteaMirror commented 2025-11-12 14:41:13 -06:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 16, 2025):

time=2025-10-16T22:08:24.294+02:00 level=WARN source=routes.go:1493 msg="corrupt manifests detected, skipping prune operation.  Re-pull or delete to clear" error="[registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M](http://registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M) EOF"

The housekeeping is being interrupted because of a corrupt manifest. Delete this and the server should do normal housekeeping when restarted.

@rick-github commented on GitHub (Oct 16, 2025): ``` time=2025-10-16T22:08:24.294+02:00 level=WARN source=routes.go:1493 msg="corrupt manifests detected, skipping prune operation. Re-pull or delete to clear" error="[registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M](http://registry.ollama.ai/library/qwen3:4b-instruct-2507-q4_K_M) EOF" ``` The housekeeping is being interrupted because of a corrupt manifest. Delete this and the server should do normal housekeeping when restarted.
GiteaMirror commented 2025-11-12 14:41:14 -06:00
Author
Owner
Copy Link

@somera commented on GitHub (Oct 16, 2025):

thx

@somera commented on GitHub (Oct 16, 2025): thx
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama-ollama#8410
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?